aws-advisor

Expert AWS Cloud Advisor for architecture design, security review, and implementation guidance. Leverages AWS MCP tools for accurate, documentation-backed answers. Use when user asks about AWS architecture, security, service selection, migrations, troubleshooting, or learning AWS. Triggers on AWS, Lambda, S3, EC2, ECS, EKS, DynamoDB, RDS, CloudFormation, CDK, Terraform, Serverless, SAM, IAM, VPC, API Gateway, or any AWS service. Do NOT use for non-AWS cloud providers or general infrastructure without AWS context.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable overview with exemplary reference and script signaling and verified bundle files. Its main weaknesses are inline boilerplate code that bloats the always-loaded body and workflows that omit explicit validation/feedback checkpoints.

Suggestions

Move the four inline IaC code examples (Terraform/Serverless/SAM/CDK) into a reference file such as references/iac-examples.md and link to it from the Code Examples section, since this is largely known Lambda boilerplate that competes for always-loaded context.

Add explicit validation/feedback checkpoints to the workflows — e.g., after running well_architected_review.py or security_review.py, verify the generated checklist against the gathered architecture before recommending, and loop back to search docs on any gap.

Tighten the Adaptive Behavior prompts and Code Examples preference questions, which restate guidance Claude would naturally follow, to further reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient via dense tables and lists, but the inline four-flavor IaC code blocks (Terraform/Serverless/SAM/CDK) are largely known Lambda-function boilerplate occupying always-loaded tokens that could be tightened or moved out, matching the "could be tightened" anchor rather than the every-token-earns-its-place anchor at 3.	2 / 3
Actionability	Provides concrete, executable guidance throughout: named MCP tools with use-cases (e.g. `aws___search_documentation`), a query-to-topic mapping table, runnable scripts (e.g. `scripts/well_architected_review.py`), and copy-paste-ready code examples, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The Standard, Architecture Review, and Security Review flows are clearly sequenced numbered steps, but none include explicit validation checkpoints or validate→fix→retry feedback loops (e.g. verifying a generated checklist against the architecture), matching the sequence-present-but-checkpoints-missing anchor at 2 rather than the explicit-validation anchor at 3.	2 / 3
Progressive Disclosure	SKILL.md is an overview with a "Reference Files" table (Load-When guidance, one level deep, verified to exist: mcp-guide.md, decision-trees.md, checklists.md) and a "Scripts" table of five verified scripts, matching the clear-overview-with-well-signaled-one-level-deep-references anchor.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states capabilities, gives rich natural-language triggers, and disambiguates scope with explicit negative guidance. No first/second-person voice or vague fluff to penalize.

Dimension	Reasoning	Score
Specificity	Names the AWS domain plus multiple concrete actions — "architecture design, security review, and implementation guidance" and "Leverages AWS MCP tools for ... documentation-backed answers" — matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly answers what ("architecture design, security review, and implementation guidance") and when ("Use when user asks about ..." / "Triggers on ..."), satisfying the both-what-and-when-with-explicit-triggers anchor; the missing-trigger cap at 2 does not apply.	3 / 3
Trigger Term Quality	Both a "Use when user asks about ..." clause and a "Triggers on AWS, Lambda, S3, EC2, ECS, EKS, DynamoDB, RDS, CloudFormation, CDK, Terraform, Serverless, SAM, IAM, VPC, API Gateway" list give broad coverage of natural terms users would say, exceeding the partial-coverage anchor at 2.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to AWS with explicit negative guidance ("Do NOT use for non-AWS cloud providers or general infrastructure without AWS context"), giving a clear niche unlikely to trigger for the wrong skill rather than the overlapping anchor at 2.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tech-leads-club/agent-skills
Commit: 9026164

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.